Skills agent-tools

📦

agent-tools

Name: agent-tools
Author: inference-sh-7

Content revision r1 Critical 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Run Cloud AI Apps from Your Agent

Teams need one workflow for many hosted AI models and media tools. This skill gives agents structured inference.sh CLI guidance for discovery, execution, and result tracking.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "agent-tools" from https://skillstore.io/skills/inference-sh-7-agent-tools.md and its manifest at https://skillstore.io/api/skills/inference-sh-7-agent-tools/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inference-sh-7-agent-tools.md Signed manifest GET /api/skills/inference-sh-7-agent-tools/manifest Signed lockfile GET /api/skills/inference-sh-7-agent-tools/lockfile

Test it

Using "agent-tools". Find an image generation app for product mockups.

Expected outcome:

A ranked shortlist of image apps.
One recommended app with why it fits.
Setup notes and approval checkpoints before execution.

Using "agent-tools". Generate a short video from a prompt and track the task.

Expected outcome:

A selected video app and required input plan.
A confirmation request before running the job.
Task tracking guidance and result retrieval steps.

Using "agent-tools". Use web search to gather current information about a topic.

Expected outcome:

A search app recommendation.
A query plan for the requested topic.
A concise result summary with source handling notes.

Security Audit

Critical

v5 • 7/9/2026 Open versioned report

Confirmed risks are concentrated in remote installer guidance that pipes downloaded content into a shell and uses dynamic command substitution. Most hardcoded URL, environment variable, filesystem, and Markdown backtick findings are documentation or legitimate CLI references. A semantic concern remains because the skill can guide public Twitter/X actions through the infsh CLI.

Files scanned

554

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (5)

Critical

references/authentication.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The command pipes a remote HTTPS response directly into a shell. A compromised endpoint, DNS path, or transport trust failure would execute attacker-controlled installer code.

Critical

references/authentication.md:44

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The reinstall command pipes a remote HTTPS response directly into a shell. This is a real remote code execution risk if the installer endpoint is compromised.

Critical

references/cli-reference.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The installation reference pipes downloaded script content directly into sh. That pattern can execute attacker-controlled code if the remote installer or delivery path is compromised.

Critical

SKILL.md:16

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The skill recommends piping a remote installer directly to sh. That can execute arbitrary code if the installer endpoint or delivery path is compromised.

High

SKILL.md:49-50 SKILL.md:78

Public External Action Automation

The skill documents running inference.sh apps that post to Twitter/X, including a direct post-tweet example. These commands can publish content through a connected account and need explicit user confirmation.

The SKILL.md examples explicitly include x/post-tweet and list Twitter/X actions. This is clear side-effecting external automation, not a pattern-match duplicate.

Capability review items (7)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:26

Shell command substitution

> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep

The manual install block evaluates a remote manifest through command substitution to choose a download URL. This increases install risk because the selected artifact source is hidden inside shell expansion.

Medium

SKILL.md:23-32

Template literal with command substitution

> ```bash

The cited manual install block contains the dynamic command-substitution download flow. It is documentation, but users or agents may execute it during installation.

Low

references/authentication.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

This URL is part of a remote installer command that downloads executable script content from the network. The URL itself is expected, but it supports a risky install flow and should remain visible as a low network risk.

Low

references/authentication.md:44

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

This URL is part of a reinstall command that downloads executable script content from the network. It supports the same risky remote installer flow as the install section.

Low

references/cli-reference.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

This URL is used in a remote installer command that fetches executable content from the network. It is expected for installation, but it is still part of a risky install path.

Low

SKILL.md:16

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

This URL is embedded in a remote installer command that fetches executable content. The URL is expected, but it supports a risky pipe-to-shell install flow.

Low

SKILL.md:26

Hardcoded URL

> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep

This URL is used inside command substitution that fetches a manifest to select a binary download. It is a real network dependency in the install path.

Risk Factors

🌐 Network access (17)

references/authentication.md:6 references/authentication.md:44 references/cli-reference.md:6 references/running-apps.md:129 SKILL.md:7 SKILL.md:11 SKILL.md:16 SKILL.md:20 SKILL.md:25 SKILL.md:26 SKILL.md:120 SKILL.md:121 SKILL.md:122 SKILL.md:123 SKILL.md:124 SKILL.md:125 SKILL.md:126

🔑 Env variables (3)

references/authentication.md:30 references/authentication.md:53 references/cli-reference.md:72

📁 Filesystem access (4)

references/cli-reference.md:84 references/cli-reference.md:84 SKILL.md:31 SKILL.md:31

⚙️ External commands (18)

SKILL.md:15-18 SKILL.md:18-20 SKILL.md:20-23 SKILL.md:23-32 SKILL.md:32-36 SKILL.md:36-54 SKILL.md:54-60 SKILL.md:60-61 SKILL.md:61-62 SKILL.md:62-63 SKILL.md:63-64 SKILL.md:64-65 SKILL.md:65-66 SKILL.md:66-67 SKILL.md:67-83 SKILL.md:83-109 SKILL.md:26 SKILL.md:23-32

Detected Patterns

Pipe to shell pattern×4

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/inference-sh-7-agent-tools/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-7-agent-tools/security.svg)](https://skillstore.io/skills/inference-sh-7-agent-tools?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-7-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-7-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-7-agent-tools.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

inference-sh-7. (2026). agent-tools security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-7-agent-tools/audits/5

BibTeX citation

@techreport{inference-sh-7-inference-sh-7-agent-tools-2026,
  author = {inference-sh-7},
  title = {agent-tools security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/inference-sh-7-agent-tools/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-tools security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh-7"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/inference-sh-7-agent-tools/audits/5"
identifiers:
  - type: other
    value: "skillstore:inference-sh-7-agent-tools:audit:5"
    description: "Skillstore immutable audit report identifier"

Compare variants

20 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

tul-sh Recommended

tul-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 26

Updated

2026-08-21

toolshell

toolshell-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 23

Updated

2026-08-21

inferen-sh

inferen-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 14

Updated

2026-08-21

tool-belt

tool-belt-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

inferencesh

inferencesh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 11

Updated

2026-08-21

inference-sh-skills

inference-sh-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-sh-7 Current

inference-sh-7-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inf-sh

inf-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

inference-skills

inference-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

skillssh

skillssh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-sh-9

inference-sh-9-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-sh-3

inference-sh-3-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

qu-skills

qu-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

infsh-skills

infsh-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

inference-sh-6

inference-sh-6-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

inference-sh-0

inference-sh-0-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

inference-shell

inference-shell-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

inference-sh-8

inference-sh-8-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

101-skills

101-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 4

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Prototype AI Features

Find hosted models, inspect schemas, generate sample inputs, and run trial jobs without building separate integrations.

Generate Media Assets

Run image, video, audio, and 3D generation apps from a consistent command workflow.

Run Search and LLM Tasks

Use search and LLM apps for research, summarization, answer generation, and task tracking.

Try These Prompts

Find an App

Use agent-tools to search inference.sh for [task]. Compare relevant apps and recommend one option.

Run a Simple Job

Use agent-tools to generate a sample input for [app]. Explain required fields and run it after I approve.

Build a Media Workflow

Use agent-tools to create a workflow that generates [asset], tracks the task, and saves the result.

Operate a Multi-App Pipeline

Use agent-tools to discover, validate, and run inference.sh apps for [pipeline]. Include cost, privacy, and confirmation checkpoints.

Best Practices

Confirm account, cost, and data sensitivity before running cloud apps.
Generate and review sample inputs before submitting a production task.
Require explicit approval before social media or other account-changing actions.

Avoid

Do not run installer commands without verifying the downloaded artifact.
Do not submit secrets, private data, or regulated content as model input without approval.
Do not automate Twitter/X actions without a clear user request and confirmation.

Frequently Asked Questions

What does this skill help an agent do?

It helps an agent use the inference.sh CLI to discover apps, prepare inputs, run tasks, and retrieve results.

Does it require an inference.sh account?

Yes. The CLI must be installed and authenticated before most commands can run.

Can it generate images and videos?

Yes. The references include image, video, audio, text, search, 3D, and utility app workflows.

Can it call Claude or OpenRouter models?

Yes. The skill includes examples for Claude through OpenRouter and other LLM app providers.

Can it post to Twitter/X?

Yes, if the connected inference.sh app and account allow it. Users should confirm every public action first.

What are the main safety concerns?

Installer commands, cloud data submission, usage costs, and account-changing automation need review before execution.

Developer Details

Author

inference-sh-7

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-7/skills/tree/main/skills/agent-tools/

Ref

3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88

Maintenance freshness

7/18/2026

Usage

8 downloads · 140 views

File structure

📁 references/

📄 app-discovery.md

📄 authentication.md

📄 cli-reference.md

📄 running-apps.md

📄 SKILL.md

More from inference-sh-7

View all

📦

remotion-render

Render Remotion Videos from TSX

Video teams need a repeatable way to turn React animations into files. This skill renders Remotion TSX through inference.sh and returns MP4 output.

Design & Creative View

View all

📦

linear-projects-write

Create and Update Linear Projects from the CLI

by Bind

Managing Linear projects through the web interface is slow when you work in the terminal or automate workflows. This skill lets you create and update projects with simple commands, so you can manage project data directly from scripts and the command line.

Productivity View

📦

web-cli-teleport

Choose Claude Code Web or CLI

by DNYoussef

Teams lose time when they pick the wrong Claude Code interface for a task. This skill recommends Web, CLI, or a hybrid handoff workflow.

Productivity View

📦

lark-doc

Manage Lark Docs and Feishu Wiki Content

by larksuite

Teams need reliable document updates without switching between tools. This skill guides Claude, Codex, and Claude Code through authenticated lark-cli workflows for Lark Docs.

Office & Reports View

📦

pptx

Create PowerPoint Presentations with Python

by AutumnsGrove

Building polished PowerPoint decks by hand is slow and hard to repeat. This skill guides Claude, Codex, and Claude Code through PPTX creation, editing, and automation with python-pptx.

Office & Reports View

📦

building-agents

Build Claude Code Agents

by C0ntr0lledCha0s

Creating reliable AI agents requires clear schemas, safe tools, and repeatable review steps. This skill guides agent design, validation, migration, and maintenance for Claude Code workflows.

Coding & Development View

📦

building-commands

Build Claude Code Slash Commands

by C0ntr0lledCha0s

Teams need repeatable AI workflows that are easy to invoke and review. This skill helps create, update, validate, and document Claude Code slash commands.

Coding & Development View

agent-tools

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (5)

Risk Factors

Detected Patterns

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Prototype AI Features

Generate Media Assets

Run Search and LLM Tasks

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details

More from inference-sh-7

remotion-render

Related Skills

linear-projects-write

web-cli-teleport

lark-doc

pptx

building-agents

building-commands